Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc4f84a4361a57a2ddc8bef0539cbe34d1c64bb2646b8024b7db52793154a4e
+oid sha256:ae84fd3f31e151654ac1b73f89b555b426cf1db67b5c6045c4ecff4e9af9a697
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbbc5bd726742a12b6558f73677c3f35b5eea225e1da22ea3386ecfbe81b869
+oid sha256:8181b5cf2858ef70571b079be880a592072c65abe5cb38e3b97de3fadda9c952
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8598e72ae541b644e48c8299e30409f566b567643961d1b93f86b310df0d19
+oid sha256:906a9e6400187d6899fb20f1e1e70a8f191fa21191db7d4f21aaf6ccce3ae8ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013505118439888718,
+  "epoch": 0.0027010236879777437,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 1.6082,
       "step": 25
+    },
+    {
+      "epoch": 0.0014045323177484267,
+      "grad_norm": 1.089220404624939,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.4618,
+      "step": 26
+    },
+    {
+      "epoch": 0.0014585527915079814,
+      "grad_norm": 0.9762293100357056,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.6464,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014585527915079814,
+      "eval_loss": 1.5239306688308716,
+      "eval_runtime": 3370.1015,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015125732652675364,
+      "grad_norm": 0.9106154441833496,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3052,
+      "step": 28
+    },
+    {
+      "epoch": 0.0015665937390270913,
+      "grad_norm": 0.9534875750541687,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.5035,
+      "step": 29
+    },
+    {
+      "epoch": 0.0016206142127866462,
+      "grad_norm": 0.9660364389419556,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.4769,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016746346865462011,
+      "grad_norm": 1.024480938911438,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.5453,
+      "step": 31
+    },
+    {
+      "epoch": 0.0017286551603057558,
+      "grad_norm": 0.892098069190979,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.3765,
+      "step": 32
+    },
+    {
+      "epoch": 0.0017826756340653107,
+      "grad_norm": 1.0651084184646606,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.4993,
+      "step": 33
+    },
+    {
+      "epoch": 0.0018366961078248656,
+      "grad_norm": 0.9315266013145447,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.5011,
+      "step": 34
+    },
+    {
+      "epoch": 0.0018907165815844206,
+      "grad_norm": 1.0802898406982422,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.6234,
+      "step": 35
+    },
+    {
+      "epoch": 0.0019447370553439753,
+      "grad_norm": 1.2187426090240479,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.5154,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019447370553439753,
+      "eval_loss": 1.4882609844207764,
+      "eval_runtime": 3370.139,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019987575291035304,
+      "grad_norm": 1.2731837034225464,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.4256,
+      "step": 37
+    },
+    {
+      "epoch": 0.002052778002863085,
+      "grad_norm": 0.9401973485946655,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.4064,
+      "step": 38
+    },
+    {
+      "epoch": 0.00210679847662264,
+      "grad_norm": 1.1949783563613892,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.4051,
+      "step": 39
+    },
+    {
+      "epoch": 0.002160818950382195,
+      "grad_norm": 1.3753553628921509,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.2702,
+      "step": 40
+    },
+    {
+      "epoch": 0.0022148394241417496,
+      "grad_norm": 1.9385082721710205,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.5789,
+      "step": 41
+    },
+    {
+      "epoch": 0.0022688598979013048,
+      "grad_norm": 1.170527696609497,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4807,
+      "step": 42
+    },
+    {
+      "epoch": 0.0023228803716608595,
+      "grad_norm": 1.255044937133789,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.4827,
+      "step": 43
+    },
+    {
+      "epoch": 0.002376900845420414,
+      "grad_norm": 1.1622134447097778,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.4609,
+      "step": 44
+    },
+    {
+      "epoch": 0.0024309213191799693,
+      "grad_norm": 1.0290035009384155,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.4929,
+      "step": 45
+    },
+    {
+      "epoch": 0.0024309213191799693,
+      "eval_loss": 1.4531553983688354,
+      "eval_runtime": 3370.0357,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 45
+    },
+    {
+      "epoch": 0.002484941792939524,
+      "grad_norm": 0.9841757416725159,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3785,
+      "step": 46
+    },
+    {
+      "epoch": 0.002538962266699079,
+      "grad_norm": 1.1201504468917847,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.4038,
+      "step": 47
+    },
+    {
+      "epoch": 0.002592982740458634,
+      "grad_norm": 1.2595245838165283,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.411,
+      "step": 48
+    },
+    {
+      "epoch": 0.0026470032142181885,
+      "grad_norm": 0.9506502747535706,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.3282,
+      "step": 49
+    },
+    {
+      "epoch": 0.0027010236879777437,
+      "grad_norm": 1.121146559715271,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.4374,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.635247689446195e+16,
+  "total_flos": 7.344684107248435e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null